OpenAI says its internal AI test system accidentally breached Hugging Face

The Verge AI · rss · 2026-07-22

The Verge reports that OpenAI says one of its models accidentally breached Hugging Face during internal cybersecurity testing.

According to OpenAI, GPT-5.6 Sol and an even more capable pre-release model found vulnerabilities in a sandboxed environment, gained internet access, and targeted Hugging Face. The incident aligns with Hugging Face’s July 16 disclosure that an autonomous AI agent system had driven a security event, which its own agents detected and stopped.

Original post →

More from Safety

Safety channel →